Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tomzx/agents --skill automate-sessiongit clone --depth 1 https://github.com/tomzx/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tomzx/agents/automate-session)<a href="https://agentmods.dev/skills/tomzx/agents/automate-session"><img src="https://agentmods.dev/badge/skills/tomzx/agents/automate-session/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tomzx/agents/automate-session"><img src="https://agentmods.dev/badge/skills/tomzx/agents/automate-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.01308 |
| Opus 5.5 | $0.00023 | $0.00523 |
| Sonnet 5.5 | $0.00011 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
automate-session scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automation Opportunities
Reflects on the current session and identifies which steps could have been handled autonomously, a scheduled agent, or a triggered hook, removing the user from the loop entirely or reducing their involvement to review-only.
Prerequisites
- A session with at least some completed work (conversation history, git changes, or both)
Steps
1. Reconstruct the session workflow
Build a chronological list of the steps taken during this session. Sources to draw from:
- Conversation turns: what did the user ask, decide, or approve?
git log --onelinesince session start: what changed?- File reads, writes, edits made during the session
- Any external tool calls (GitHub, Slack, etc.)
Produce a numbered step-by-step trace of the session as if writing a runbook someone else would follow.
2. Classify each step by automation potential
For each step in the trace, assign one of three labels:
| Label | Meaning |
|---|---|
| Auto | Could run fully autonomously with no human input — deterministic, low-risk, well-scoped |
| Review-gate | An agent could execute it, but a human checkpoint (approve / reject) makes sense before or after |
| Human | Requires human judgment, creative direction, or irreversible external action with unclear scope |
A step qualifies as Auto if:
- Its inputs are available programmatically (git state, file content, API response)
- Its output is verifiable (tests pass, lint clean, diff is small and scoped)
- Failure is detectable and recoverable without human intervention
- It follows a pattern used repeatedly in prior sessions
A step is Review-gate if it is automatable but touches shared state (pushes to a remote, sends a message, opens a PR) or produces output a human should sanity-check before it propagates.
A step is Human if it involves priority trade-offs, novel design decisions, or communication requiring context only the user holds.
3. Identify the automation patterns
Group the Auto and Review-gate steps into one or more named automation patterns. For each pattern, describe:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago Changed · +3 lines a3379606ce66
- 2mo ago First seen · 139 lines · 57 tokens per session scan A 4ba771df8fec
automate-session is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,308 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.